Markov Decision Problems and State-Action Frequencies

DOI10.1137/0329043zbMath0733.90075OpenAlexW2126534522MaRDI QIDQ3360681

Adam Shwartz, Eitan Altman

Publication date: 1991

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/0329043

zbMATH Keywords

adaptive controlconstrained optimizationcountable state and action spacescontrolled Markov chainstate-action frequenciesstationary policiesaverage cost functionalsnonstationary controlvariability-sensitive optimization

Mathematics Subject Classification ID

Management decision making, including multiple objectives (90B50) Queueing theory (aspects of probability theory) (60K25) Queues and service in operations research (90B22) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Optimal stochastic control (93E20) Sample path properties (60G17) Markov and semi-Markov decision processes (90C40)

Related Items (17)

Markov Decision Processes with Asymptotic Average Failure Rate Constraint ⋮ Asymptotic properties of constrained Markov Decision Processes ⋮ Constrained Semi-Markov decision processes with average rewards ⋮ Linear programming formulation of MDPs in countable state space: The multichain case ⋮ The Linear Program approach in multi-chain Markov Decision Processes revisited ⋮ Discounted continuous-time constrained Markov decision processes in Polish spaces ⋮ Adaptive control of constrained Markov chains: Criteria and policies ⋮ Sensitivity of constrained Markov decision processes ⋮ Constrained cost-coupled stochastic games with independent state processes ⋮ Discrete-Time Semi-Markov Random Evolutions and their Applications ⋮ Sample path optimality for a Markov optimization problem ⋮ Queuing with future information ⋮ OPTIMAL MIXING OF MARKOV DECISION RULES FOR MDP CONTROL ⋮ Optimality of Mixed Policies for Average Continuous-Time Markov Decision Processes with Constraints ⋮ Constrained denumerable state non-stationary MDPs with expected total reward criterion ⋮ Zero-sum constrained stochastic games with independent state processes ⋮ Notes on average Markov decision processes with a minimum-variance criterion

This page was built for publication: Markov Decision Problems and State-Action Frequencies